Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
updated name
Browse files
app.py
CHANGED
@@ -1,28 +1,39 @@
|
|
1 |
import streamlit as st
|
2 |
|
3 |
st.set_page_config(
|
4 |
-
page_title="arXiv-GPT",
|
5 |
page_icon="π",
|
6 |
)
|
7 |
|
8 |
-
st.write("# Welcome to
|
9 |
|
10 |
st.sidebar.success("Select a function above.")
|
11 |
st.sidebar.markdown("Current functions include visualizing papers in the arxiv embedding, searching for similar papers to an input paper or prompt phrase, or answering quick questions.")
|
12 |
|
13 |
st.markdown(
|
14 |
"""
|
15 |
-
arXiv+GPT is a framework for searching and
|
16 |
-
the [arXiv](https://arxiv.org/) using the context
|
17 |
-
large language models (LLMs) to better link paper contexts
|
18 |
|
19 |
**π Select a tool from the sidebar** to see some examples
|
20 |
of what this framework can do!
|
21 |
|
22 |
-
###
|
23 |
- `Paper search` looks for relevant papers given an arxiv id or a question.
|
24 |
- `Arxiv embedding` shows the landscape of current galaxy evolution papers (astro-ph.GA)
|
25 |
- `QA sources` brings it all together to give concise answers to questions with primary sources and relevant papers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
"""
|
27 |
)
|
28 |
|
@@ -42,7 +53,7 @@ st.markdown(
|
|
42 |
- Jump into our [documentation](https://docs.streamlit.io)
|
43 |
- Contribute!
|
44 |
|
45 |
-
|
46 |
|
47 |
"""
|
48 |
)
|
|
|
1 |
import streamlit as st
|
2 |
|
3 |
st.set_page_config(
|
4 |
+
page_title="Pathfinder (formerly arXiv-GPT)",
|
5 |
page_icon="π",
|
6 |
)
|
7 |
|
8 |
+
st.write("# Welcome to Pathfinder! π")
|
9 |
|
10 |
st.sidebar.success("Select a function above.")
|
11 |
st.sidebar.markdown("Current functions include visualizing papers in the arxiv embedding, searching for similar papers to an input paper or prompt phrase, or answering quick questions.")
|
12 |
|
13 |
st.markdown(
|
14 |
"""
|
15 |
+
Pathfinder (formerly called arXiv+GPT) is a framework for searching and
|
16 |
+
visualizing papers on the [arXiv](https://arxiv.org/) using the context
|
17 |
+
sensitivity from modern large language models (LLMs) to better link paper contexts.
|
18 |
|
19 |
**π Select a tool from the sidebar** to see some examples
|
20 |
of what this framework can do!
|
21 |
|
22 |
+
### Tool summary:
|
23 |
- `Paper search` looks for relevant papers given an arxiv id or a question.
|
24 |
- `Arxiv embedding` shows the landscape of current galaxy evolution papers (astro-ph.GA)
|
25 |
- `QA sources` brings it all together to give concise answers to questions with primary sources and relevant papers.
|
26 |
+
|
27 |
+
This is not meant to be a replacement to existing tools like the
|
28 |
+
[ADS](https://ui.adsabs.harvard.edu/),
|
29 |
+
[arxivsorter](https://www.arxivsorter.org/), but rather a supplement to find papers
|
30 |
+
that otherwise might be missed during a literature survey.
|
31 |
+
It is also only trained on astro-ph.GA (astrophysics of galaxies) papers currently,
|
32 |
+
if you are interested in extending it please reach out!
|
33 |
+
|
34 |
+
The image below shows a representation of all the astro-ph.GA papers that can be explored in more detail
|
35 |
+
using the `Arxiv embedding` page. The papers tend to cluster together by similarity, and result in an
|
36 |
+
atlas that shows well studied (forests) and currently uncharted areas (water).
|
37 |
"""
|
38 |
)
|
39 |
|
|
|
53 |
- Jump into our [documentation](https://docs.streamlit.io)
|
54 |
- Contribute!
|
55 |
|
56 |
+
Pathfinder is developed and maintained by [UniverseTBD](https://universetbd.org/). Updates on [huggingface](https://huggingface.co/universeTBD) or [twitter](https://twitter.com/universe_tbd).
|
57 |
|
58 |
"""
|
59 |
)
|